Individualized Studies of Triggers of Paroxysmal Atrial Fibrillation: The I-STOP-AFib Randomized Clinical Trial

Abstract

Importance: Atrial fibrillation (AF) is the most common arrhythmia. Although patients have reported that various exposures determine when and if an AF event will occur, a prospective evaluation of patient-selected triggers has not been conducted, and the utility of characterizing presumed AF-related triggers for individual patients remains unknown.

Objective: To test the hypothesis that n-of-1 trials of self-selected AF triggers would enhance AF-related quality of life.

Design, setting, and participants: A randomized clinical trial lasting a minimum of 10 weeks tested a smartphone mobile application used by symptomatic patients with paroxysmal AF who owned a smartphone and were interested in testing a presumed AF trigger. Participants were screened between December 22, 2018, and March 29, 2020.

Interventions: n-of-1 Participants received instructions to expose or avoid self-selected triggers in random 1-week blocks for 6 weeks, and the probability their trigger influenced AF risk was then communicated. Controls monitored their AF over the same time period.

Main outcomes and measures: AF was assessed daily by self-report and using a smartphone-based electrocardiogram recording device. The primary outcome comparing n-of-1 and control groups was the Atrial Fibrillation Effect on Quality-of-Life (AFEQT) score at 10 weeks. All participants could subsequently opt for additional trigger testing.

Results: Of 446 participants who initiated (mean [SD] age, 58 [14] years; 289 men [58%]; 461 White [92%]), 320 (72%) completed all study activities. Self-selected triggers included caffeine (n = 53), alcohol (n = 43), reduced sleep (n = 31), exercise (n = 30), lying on left side (n = 17), dehydration (n = 10), large meals (n = 7), cold food or drink (n = 5), specific diets (n = 6), and other customized triggers (n = 4). No significant differences in AFEQT scores were observed between the n-of-1 vs AF monitoring-only groups. In the 4-week postintervention follow-up period, significantly fewer daily AF episodes were reported after trigger testing compared with controls over the same time period (adjusted relative risk, 0.60; 95% CI, 0.43- 0.83; P < .001). In a meta-analysis of the individualized trials, only exposure to alcohol was associated with significantly heightened risks of AF events.

Conclusions and relevance: n-of-1 Testing of AF triggers did not improve AF-associated quality of life but was associated with a reduction in AF events. Acute exposure to alcohol increased AF risk, with no evidence that other exposures, including caffeine, more commonly triggered AF.

Trial registration: ClinicalTrials.gov Identifier: NCT03323099.

Figure 1.. CONSORT Diagram of Participant Screening, Consent, Randomization, and Study Completion

AV indicates atrioventricular; AFEQT, Atrial Fibrillation Effect on Quality-of-Life; ECG, electrocardiogram. ^aReasons for ineligibility are not mutually exclusive. ^bIncludes 1 participant who did not initiate 10-week period.

Figure 2.. Network Meta-analyses Odds Ratios for Self-reported AF During Trigger Exposure vs Avoidance in Intention to Treat and Per Protocol Combining All n-of-1 Trials Throughout the Study

Numbers indicate number of events/number of days reported. AF indicates atrial fibrillation; Crl, credible interval; OR, odds ratio.